Covid-19 Anaylsis

This project analyzes the state of South Florida COVID-19 vaccinations. All data is provided by the Center for Disease Control (CDC).

Updated: 8/6/2021

Data Source: https://data.cdc.gov/Vaccinations/COVID-19-Vaccinations-in-the-United-States-County/8xkx-amqh

Install Libraries

#install.packages("tidyverse")
#install.packages("dplyr")
#install.packages("plotly")

Load Libraries

library(tidyverse)
library(ggplot2)
library(dplyr) 
library(plotly)

CSV Files

# Covid vaccine data
us_covid_vaccination_csv <- "COVID-19_Vaccinations_in_the_United_States_County.csv"

# Covid cases and deaths data
us_covid_cases_and_deaths_csv <- "United_States_COVID-19_Cases_and_Deaths_by_State_over_Time.csv"

# Florida county deaths data
florida_county_deaths_csv <- "COVID-19_Deaths_FL_County.csv"

Import Data

# Vaccination Data
# importing the data
vaccData <- read_csv(covid_vaccination_csv) 

Rows: 751336 Columns: 27
-- Column specification ---------------------------------------------------------------------------------------------------------------
Delimiter: ","
chr  (9): Date, FIPS, Recip_County, Recip_State, SVI_CTGY, Series_Complete_Pop_Pct_SVI, Series_Complete_12PlusPop_Pct_SVI, Series_C...
dbl (18): MMWR_week, Series_Complete_Pop_Pct, Series_Complete_Yes, Series_Complete_12Plus, Series_Complete_12PlusPop_Pct, Series_Co...

i Use `spec()` to retrieve the full column specification for this data.
i Specify the column types or set `show_col_types = FALSE` to quiet this message.

vaccData$Date <- as.Date(vaccData$Date, format = "%m/%d/%Y")  #set date column to date

# arranging the data to show chronologically 
vaccData %>% arrange(Date)

# Covid-19 Case Data
# Importing the data
covidCases <- read_csv(us_covid_cases_and_deaths_csv)

Rows: 33240 Columns: 15
-- Column specification ---------------------------------------------------------------------------------------------------------------
Delimiter: ","
chr  (5): submission_date, state, created_at, consent_cases, consent_deaths
dbl (10): tot_cases, conf_cases, prob_cases, new_case, pnew_case, tot_death, conf_death, prob_death, new_death, pnew_death

i Use `spec()` to retrieve the full column specification for this data.
i Specify the column types or set `show_col_types = FALSE` to quiet this message.

# set date column to date
covidCases$submission_date <- as.Date(covidCases$submission_date, format = "%m/%d/%Y")  

# Renaming columns for readability
covidCases$Date <- covidCases$submission_date
covidCases$`New Cases` <- covidCases$new_case
covidCases$`New Deaths` <- covidCases$new_death

# arranging the data to show chronologically 
covidCases %>% arrange(submission_date)

# FL County Covid Death Data 
# Importing the data
covidCountyFL <- read_csv(florida_county_deaths_csv)

Rows: 67 Columns: 8
-- Column specification ---------------------------------------------------------------------------------------------------------------
Delimiter: ","
chr (5): Date, State, County name, Urban Rural Code, Footnote
dbl (1): FIPS County Code

i Use `spec()` to retrieve the full column specification for this data.
i Specify the column types or set `show_col_types = FALSE` to quiet this message.

# set date column to date
covidCountyFL$Date <- as.Date(covidCountyFL$Date, format = "%m/%d/%y")

# arranging the data to show chronologically 
covidCountyFL %>% arrange(Date)

Data Preparation

# US Daily Vaccinations
# New dataframea of total US daily vaccinations and percentage 
usVacTot <- aggregate(Series_Complete_Yes ~ Date, data = vaccData, sum) 
usVacTotPct <- aggregate(Series_Complete_Pop_Pct ~ Date, data = vaccData, mean) 

usVac12 <- aggregate(Series_Complete_12Plus ~ Date, data = vaccData, sum)  
usVac12Pct <- aggregate(Series_Complete_12PlusPop_Pct ~ Date, data = vaccData, mean)  

usVac18 <- aggregate(Series_Complete_18Plus ~ Date, data = vaccData, sum)   
usVac18Pct <- aggregate(Series_Complete_18PlusPop_Pct ~ Date, data = vaccData, mean)   

usVac65 <- aggregate(Series_Complete_65Plus ~ Date, data = vaccData, sum)   
usVac65Pct <- aggregate(Series_Complete_65PlusPop_Pct ~ Date, data = vaccData, mean)   

# Merging the dataframes into one total us daily vaccination rates
usVaccs <- merge(merge(merge(usVacTot, usVac12, by = "Date"), 
                       usVac18, by = "Date"), 
                 usVac65, by = "Date")
usVaccs

# Florida Daily Vaccinations
# filtering for only FL data
vaccFL <- (filter(vaccData, Recip_State == 'FL')) %>%                      
  
  # selecting useful columns
    subset(select = c(Date, Recip_State, Series_Complete_12Plus, Series_Complete_12PlusPop_Pct, 
                      Series_Complete_18Plus, Series_Complete_18PlusPop_Pct, 
                      Series_Complete_65Plus, Series_Complete_65PlusPop_Pct)) %>%  
  # arranging the data to show chronologically
  arrange(Date)                                                             

vaccFL

# US Daily Covid
# New dataframe of total US daily new cases and deaths 
usCases <- aggregate(`New Cases` ~ Date, data = covidCases, sum)    # daily total new cases
usDeaths <- aggregate(`New Deaths` ~ Date, data = covidCases, sum)  # daily deaths

usCovid <- merge(usCases, usDeaths, by = "Date")
usCovid

# Florida Daily Covid-19
# Filter for only FL data
covidFL <- filter(covidCases, state == 'FL') %>%  
  
  # selecting useful columns
    subset(select = c(Date, `New Cases`, `New Deaths`)) %>%   
  
  # arranging the data to show chronologically
  arrange(Date)                                                             

covidFL

# Broward County Vaccination Data
# filter for only broward vaccine 
BrowardVac <- filter(vaccData, Recip_County  == 'Broward County') %>%
  
  # selecting useful columns
    subset(select = c(Date, Series_Complete_Yes, Series_Complete_12Plus, Series_Complete_12PlusPop_Pct, 
                      Series_Complete_18Plus, Series_Complete_18PlusPop_Pct, 
                      Series_Complete_65Plus, Series_Complete_65PlusPop_Pct)) %>%
  
  # arranging the data to show chronologically
    arrange(Date) 

BrowardVac

# South Florida Counties Covid-19 Deaths
# Filter for certain FL countries
southFLDeaths = filter(covidCountyFL, `County name` == 'Miami-Dade County' | `County name` == 'Broward County'| `County name` == 'Palm Beach County') %>%
  
  # selecting useful columns
    subset(select = c(Date, `County name`, `Deaths involving COVID-19`, `Deaths from All Causes`)) %>%
  
  # arranging the data to show chronologically
    arrange(Date)                                                             
  
southFLDeaths

# Miami Vaccination data
# filtering for only FL data
miamiVacc <- (filter(vaccData, Recip_County == "Miami-Dade County")) %>%                      
  
  # selecting useful columns
    subset(select = c(Date, Series_Complete_12Plus, Series_Complete_12PlusPop_Pct, 
                      Series_Complete_18Plus, Series_Complete_18PlusPop_Pct, 
                      Series_Complete_65Plus, Series_Complete_65PlusPop_Pct)) %>%  
  # arranging the data to show chronologically
  arrange(Date)                                                             

miamiVacc

Data Analytics

Covid-19 Case Data

Bar Plot: New Cases in US vs. Date

# Kelly Rivera
usCaseGraph <- ggplot(mapping = aes(x = `Date`, 
                                    y = `New Cases`/1000, 
                                    color = `New Cases`, 
                                    text = paste("<br>Date:", Date,
                                                 "<br>New Cases:", `New Cases`/1000))) +
  
  geom_col(data = usCovid, show.legend = FALSE) +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "United States: Daily New Covid Cases",
       subtitle = "Source: CDC",
       x = "Date",
       y = "Number of Cases (thousands)")

ggplotly(usCaseGraph, tooltip = c("text"))

US New Cases Line Graph

# Amanda Ibarra
USCases<-ggplot(data=usCovid, aes(x= `Date`, y= `New Cases`)) +
  geom_line()+
  geom_point(size = 1)+ labs(title = "New Cases in United States",
         x = "Date",
         y = "New Cases",
         subtitle = "Source: CDC") +
  scale_colour_discrete("County")

ggplotly(USCases)

Bar Plot: New Deaths in US vs. Date

# Kelly Rivera
usDeathsGraph <- ggplot(mapping = aes(x = `Date`, 
                                    y = `New Deaths`, 
                                    color = `New Deaths`, 
                                    text = paste("<br>Date:", Date,
                                                 "<br>New Deaths:", `New Deaths`))) +
  
  geom_col(data = usCovid, show.legend = FALSE) +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "United States: Daily New Covid Deaths",
       subtitle = "Source: CDC",
       x = "Date",
       y = "Number of Deaths")

newUsDeathsGraph <- usDeathsGraph+scale_color_gradient(low="firebrick4", high="red") # changing the gradient colors from defult blue

ggplotly(newUsDeathsGraph, tooltip = c("text"))

Line Plot: New Cases in FL vs. Date

# Rachel Tuffy
graph1 <- ggplot(data = covidFL, mapping = aes(y = `New Cases`/1000, x = `Date`)) +
  geom_smooth(method = "loess", type = "scatter") +
  geom_line() +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "New Cases in FL by Date",
       x = "Date",
       y = "New Cases (thousands)")

Ignoring unknown parameters: type

ggplotly(graph1)

`geom_smooth()` using formula 'y ~ x'

Line Plot: New Cases in FL vs. Date

# Rachel Tuffy
graph1 <- ggplot(data = covidFL, mapping = aes(y = `New Cases`/1000, x = `Date`)) +
  geom_smooth(method = "loess", type = "scatter") +
  geom_line() +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "New Cases in FL by Date",
       x = "Date",
       y = "New Cases (thousands)")

Ignoring unknown parameters: type

ggplotly(graph1)

`geom_smooth()` using formula 'y ~ x'

Bar Plot: New Cases in FL vs. Date

# Kelly Rivera
flCaseGraph <- ggplot(mapping = aes(x = `Date`, 
                                    y = `New Cases`/1000, 
                                    color = `New Cases`, 
                                    text = paste("<br>Date:", Date,
                                                 "<br>New Cases:", `New Cases`/1000))) +
  
  geom_col(data = covidFL, show.legend = FALSE) +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "Florida: Daily New Covid Cases",
       subtitle = "Source: CDC",
       x = "Date",
       y = "Number of Cases (thousands)")

ggplotly(flCaseGraph, tooltip = c("text"))

Line Plot: New Deaths in FL vs. Date

# Kelly Rivera
flDeathsGraph <- ggplot(mapping = aes(x = `Date`, 
                                    y = `New Deaths`, 
                                    color = `New Deaths`, 
                                    text = paste("<br>Date:", Date,
                                                 "<br>New Deaths:", `New Deaths`))) +
  
  geom_col(data = covidFL, show.legend = FALSE) +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "Florida: Daily New Covid Deaths",
       subtitle = "Source: CDC",
       x = "Date",
       y = "Number of Deaths")

newFLDeathsGraph <- flDeathsGraph+scale_color_gradient(low="firebrick4", high="red") # changing the gradient colors from default blue

ggplotly(newFLDeathsGraph, tooltip = c("text"))

Vaccination Data

Barplot: Percenatge of US vaccinations by Age Group

# Kelly Rivera
usCompSeriesPerc <- ggplot(mapping = aes(x = Date,
                                      y = Series_Complete_Yes)) + 
                  geom_col(data = usVaccs) +
                  scale_x_date(date_labels = "%b %Y") +
                  labs(title = "US Fully Vaccationate Percentage",
                         x = "Date",
                         y = "Series Complete Percentage (%)",
                         subtitle = "Source: CDC") +
                  scale_colour_discrete("County")

ggplotly(usCompSeriesPerc)

Barplot: Numbers of US vaccinations by Age Group

# Kelly Rivera
usCompSeries <- ggplot(mapping = aes(x = Date)) + 
                  geom_line(data = usVaccs, mapping = aes(y = Series_Complete_12Plus/1000000), color = "blue") +
                  geom_line(data = usVaccs, mapping = aes(y = Series_Complete_18Plus/1000000), color = "red") +
                  geom_line(data = usVaccs, mapping = aes(y = Series_Complete_65Plus/1000000), color = "yellow") +
                  scale_x_date(date_labels = "%b %Y") +
                  labs(title = "US Fully Vaccationate",
                         x = "Date",
                         y = "Number of Series Complete (millions)",
                         subtitle = "Source: CDC") +
                  scale_colour_discrete("County")

ggplotly(usCompSeries)

Barplot: Percenatge of FL vaccinations by Age Group

Barplot: Numbers of FL vaccinations by Age Group

# Kelly Rivera
flCompSeries <- ggplot(mapping = aes(x = Date)) + 
                  geom_line(data = vaccFL, mapping = aes(y = Series_Complete_12Plus), color = "blue") +
                  geom_line(data = vaccFL, mapping = aes(y = Series_Complete_18Plus), color = "red") +
                  geom_line(data = vaccFL, mapping = aes(y = Series_Complete_65Plus), color = "yellow") +
                  scale_x_date(date_labels = "%b %Y") +
                  labs(title = "US Fully Vaccationate",
                         x = "Date",
                         y = "Number of Series Complete (millions)",
                         subtitle = "Source: CDC") +
                  scale_colour_discrete("County")

ggplotly(flCompSeries)

Bar plot: Broward Vaccination Population

# Amanda Ibarra
BrowardFullyVac<-ggplot(BrowardVac, aes(x=Date, y=Series_Complete_Yes)) + 
  geom_bar(stat = "identity", color= "orange") + scale_x_date(date_labels = "%b %Y") +
  labs(title = "Broward County: Fully Vaccinated Population",
         x = "Date",
         y = "Series Complete",
         subtitle = "Source: CDC") +
  scale_colour_discrete("County")
ggplotly(BrowardFullyVac)

Bar plot: Broward Vaccination 12 Plus

# Amanda Ibarra
Broward12PlusVac <-ggplot(BrowardVac, aes(x=Date, y=Series_Complete_12Plus)) + 
  geom_bar(stat = "identity", color= "red") + scale_x_date(date_labels = "%b %Y") +
  labs(title = "Broward County: Fully Vaccinated 12 Plus Population",
         x = "Date",
         y = "Series Complete",
         subtitle = "Source: CDC") +
  scale_colour_discrete("County")
ggplotly(Broward12PlusVac)

Bar plot: Broward Vaccination 18 Plus

# Amanda Ibarra
Broward18PlusVac <-ggplot(BrowardVac, aes(x=Date, y=Series_Complete_18Plus)) + 
  geom_bar(stat = "identity", color= "blue") + scale_x_date(date_labels = "%b %Y") +
  labs(title = "Broward County: Fully Vaccinated 18 Plus Population",
         x = "Date",
         y = "Series Complete",
         subtitle = "Source: CDC") +
  scale_colour_discrete("County")
ggplotly(Broward18PlusVac)

Bar plot: Broward Vaccination 65 Plus

# Amanda Ibarra
Broward65PlusVac <-ggplot(BrowardVac, aes(x=Date, y=Series_Complete_65Plus)) + 
  geom_bar(stat = "identity", color= "orange") +  scale_x_date(date_labels = "%b %Y") +
  labs(title = "Broward County: Fully Vaccinated 65 Plus Population",
         x = "Date",
         y = "Series Complete",
         subtitle = "Source: CDC") +
  scale_colour_discrete("County")
ggplotly(Broward65PlusVac)

Bar Plot: Covid Deaths for SoFL counties

# Manuela Montoya
ggplot(southFLDeaths,mapping = aes(y= `Deaths involving COVID-19`/1000 ,x =`County name`, fill = `County name`)) +
  geom_bar(stat = 'identity', show.legend = FALSE) +
  labs(title = "South Florida: Deaths Involving COVID-19",
       y = "Number of Deaths (thousands)", x = 'County Name ')

Miami vaccinations Age 12+

# Manuela Montoya
Age12 <-ggplot(miamiVacc, mapping = aes(y= Series_Complete_12Plus, x = Date)) +
  geom_bar(stat = 'identity', color = "blue") +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "Miami Vaccination Numbers: Age 12+",
       y = "Vaccination Numbers",
       x = 'Date')

ggplotly(Age12)

Miami vaccinations Age 18+

# Manuela Montoya
Age18 <-ggplot(miamiVacc, mapping = aes(y= Series_Complete_18Plus, x = Date)) +
  geom_bar(stat = 'identity', color = "red") +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "Miami Vaccination Numbers: Age 18+",
       y = "Vaccination Numbers",
       x = 'Date')

ggplotly(Age18)

Miami vaccinations Age 65+

# Manuela Montoya
Age65 <- ggplot(miamiVacc, mapping = aes(y= Series_Complete_65Plus, x = Date)) +
  geom_bar(stat = 'identity', color = 'orange') +
  scale_x_date(date_labels = "%b %Y") +
  labs(title = "Miami Vaccination Numbers: Age 65+",
       y = "Vaccination Numbers",
       x = 'Date')

ggplotly(Age65)